Predictors of Outpatients’ No-Show: Big Data Analytics using Apache Spark

Daghistani, Tahani; AlGhamdi, Huda; Alshammari, Riyad; AlHazme, Raed H.

doi:10.21203/rs.3.rs-33216/v3

Cited by 5 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…14 This finding provides an additional important feature to consider in the development of prediction models for missed appointments, as it represents a previously unassessed predictor in such models. [43][44][45] Because of the cross-sectional nature of our data, we are unable to draw temporal relationships between being a portal user and no-shows. An area of future research could be evaluating differences in no shows between appointments made through the portal compared to other means.…”

Section: Discussionmentioning

confidence: 99%

Characteristics of Adult Primary Care Patients Who Use the Patient Portal: A Cross-Sectional Analysis

et al. 2022

View full text Add to dashboard Cite

Background: The patient portal allows patients to engage with their healthcare team beyond the clinical encounter. While portals can improve patient outcomes, there may be disparities in which patients access the portal by sociodemographic factors. Understanding the characteristics of patients who use the portal could help design future interventions to expand portal adoption. Objectives: This study aimed to (1) examine the socioeconomic factors, comorbid conditions, and healthcare utilization among patients of a large academic primary care network who are users and non-users of the patient portal; and (2) describe the portal functions most frequently utilized. Methods: We included all adult patients at Atrium Health Wake Forest Baptist who had at least two primary care visits between 2018 and 2019. Patients' demographics, comorbidities, healthcare utilization, and portal function usage were extracted from the electronic health record and merged with census data (income, education, and unemployment) from the American Community Survey. A myWakeHealth portal user was defined as a patient who used a bidirectional portal function at least once during the study period. We used multivariable logistic regression to determine which patient characteristics were independently associated with being a portal user. Results: Of the 178,720 patients who met inclusion criteria, 32% (N=57,122) were users of myWakeHealth. Compared to non-users, users were more likely to be 18-64 years of age, female, non-Hispanic white, married, commercially insured, have higher disease burden, and have lower healthcare utilization. Patients residing in areas with the highest educational attainment had 51% higher odds of being a portal user than the lowest (p<0.001). Among portal users, the most commonly used function was messaging clinic providers. Conclusions: We found that patient demographics and area socioeconomic factors were associated with patient portal adoption. These findings suggest that efforts to improve portal adoption should be targeted at vulnerable patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Characteristics of Adult Primary Care Patients Who Use the Patient Portal: A Cross-Sectional Analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…They build predictive models with machine learning algorithm JRip [32] and Hoeffding tree algorithm [33]. In [31], data used is provided by their national health center of authors' country. Five algorithms, random forest, gradient boosting, logistic regression, SVM, and multilayer perceptron, were used [34].…”

Section: Related Workmentioning

confidence: 99%

Efficient Prediction of Missed Clinical Appointment Using Machine Learning

Qureshi

Maqbool

Mirza

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Public health and its related facilities are crucial for thriving cities and societies. The optimum utilization of health resources saves money and time, but above all, it saves precious lives. It has become even more evident in the present as the pandemic has overstretched the existing medical resources. Specific to patient appointment scheduling, the casual attitude of missing medical appointments (no-show-ups) may cause severe damage to a patient’s health. In this paper, with the help of machine learning, we analyze six million plus patient appointment records to predict a patient’s behaviors/characteristics by using ten different machine learning algorithms. For this purpose, we first extracted meaningful features from raw data using data cleaning. We applied Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling Method (Adasyn), and random undersampling (RUS) to balance our data. After balancing, we applied ten different machine learning algorithms, namely, random forest classifier, decision tree, logistic regression, XG Boost, gradient boosting, Adaboost Classifier, Naive Bayes, stochastic gradient descent, multilayer perceptron, and Support Vector Machine. We analyzed these results with the help of six different metrics, i.e., recall, accuracy, precision, F1-score, area under the curve, and mean square error. Our study has achieved 94% recall, 86% accuracy, 83% precision, 87% F1-score, 92% area under the curve, and 0.106 minimum mean square error. Effectiveness of presented data cleaning and feature selection is confirmed by better results in all training algorithms. Notably, recall is greater than 75%, accuracy is greater than 73%, F1-score is more significant than 75%, MSE is lesser than 0.26, and AUC is greater than 74%. The research shows that instead of individual features, combining different features helps make better predictions of a patient’s appointment status.

show abstract

“…It was observed that 58% of the reviewed papers [15, were based on BD predictive analytics, 18% BD prescriptive analytics [103][104][105] , 11% BD descriptive analytics [15, , whiles 9% (A+B) [100][101][102][103][104][105] and 5% (B+C) [106][107][108] . Few studies in BDA used prescriptive analytics (see Table A1 in Appendix); this can be attributed to fact that big data prescriptive analytics is in its early stage.…”

Section: Methodsmentioning

confidence: 99%

“…Additionally, it was observed that some studies [15,69,73,87,89,93,95,98,101,122] adopted ensemble learning methods, like the random forest, boosting, and bagging, to enhance the power of EL techniques in BDA. ML algorithm's hybridisation is an excellent technique to compensate for the weakness in the individual algorithm [9] .…”

Section: Big Data Platforms Tool In Bdamentioning

confidence: 99%

See 1 more Smart Citation

A mini-review of machine learning in big data analytics: Applications, challenges, and prospects

Nti

Quarcoo

Aning

et al. 2022

Big Data Min. Anal.

View full text Add to dashboard Cite

The availability of digital technology in the hands of every citizenry worldwide makes an available unprecedented massive amount of data. The capability to process these gigantic amounts of data in real-time with Big Data Analytics (BDA) tools and Machine Learning (ML) algorithms carries many paybacks. However, the high number of free BDA tools, platforms, and data mining tools makes it challenging to select the appropriate one for the right task. This paper presents a comprehensive mini-literature review of ML in BDA, using a keyword search; a total of 1512 published articles was identified. The articles were screened to 140 based on the study proposed novel taxonomy. The study outcome shows that deep neural networks (15%), support vector machines (15%), artificial neural networks (14%), decision trees (12%), and ensemble learning techniques (11%) are widely applied in BDA.The related applications fields, challenges, and most importantly the openings for future research, are detailed.

show abstract

Predictors of Outpatients’ No-Show: Big Data Analytics using Apache Spark

Cited by 5 publications

References 4 publications

Characteristics of Adult Primary Care Patients Who Use the Patient Portal: A Cross-Sectional Analysis

Characteristics of Adult Primary Care Patients Who Use the Patient Portal: A Cross-Sectional Analysis

Efficient Prediction of Missed Clinical Appointment Using Machine Learning

A mini-review of machine learning in big data analytics: Applications, challenges, and prospects

Contact Info

Product

Resources

About